Commit f2902a2f authored by Christoph Hellwig's avatar Christoph Hellwig Committed by Michael Ellerman

powerpc: use the generic dma coherent remap allocator

This switches to using common code for the DMA allocations, including
potential use of the CMA allocator if configured.

Switching to the generic code enables DMA allocations from atomic
context, which is required by the DMA API documentation, and also
adds various other minor features drivers start relying upon.  It
also makes sure we have on tested code base for all architectures
that require uncached pte bits for coherent DMA allocations.

Another advantage is that consistent memory allocations now share
the general vmalloc pool instead of needing an explicit careout
from it.
Signed-off-by: default avatarChristoph Hellwig <hch@lst.de>
Tested-by: Christophe Leroy <christophe.leroy@c-s.fr> # tested on 8xx
Signed-off-by: default avatarMichael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20190814132230.31874-2-hch@lst.de
parent 555e2817
...@@ -1141,18 +1141,6 @@ config TASK_SIZE ...@@ -1141,18 +1141,6 @@ config TASK_SIZE
default "0x80000000" if PPC_8xx default "0x80000000" if PPC_8xx
default "0xc0000000" default "0xc0000000"
config CONSISTENT_SIZE_BOOL
bool "Set custom consistent memory pool size"
depends on ADVANCED_OPTIONS && NOT_COHERENT_CACHE
help
This option allows you to set the size of the
consistent memory pool. This pool of virtual memory
is used to make consistent memory allocations.
config CONSISTENT_SIZE
hex "Size of consistent memory pool" if CONSISTENT_SIZE_BOOL
default "0x00200000" if NOT_COHERENT_CACHE
config PIN_TLB config PIN_TLB
bool "Pinned Kernel TLBs (860 ONLY)" bool "Pinned Kernel TLBs (860 ONLY)"
depends on ADVANCED_OPTIONS && PPC_8xx && \ depends on ADVANCED_OPTIONS && PPC_8xx && \
......
...@@ -148,21 +148,15 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); ...@@ -148,21 +148,15 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot);
*/ */
#include <asm/fixmap.h> #include <asm/fixmap.h>
#ifdef CONFIG_HIGHMEM
#define KVIRT_TOP PKMAP_BASE
#else
#define KVIRT_TOP FIXADDR_START
#endif
/* /*
* ioremap_bot starts at that address. Early ioremaps move down from there, * ioremap_bot starts at that address. Early ioremaps move down from there,
* until mem_init() at which point this becomes the top of the vmalloc * until mem_init() at which point this becomes the top of the vmalloc
* and ioremap space * and ioremap space
*/ */
#ifdef CONFIG_NOT_COHERENT_CACHE #ifdef CONFIG_HIGHMEM
#define IOREMAP_TOP ((KVIRT_TOP - CONFIG_CONSISTENT_SIZE) & PAGE_MASK) #define IOREMAP_TOP PKMAP_BASE
#else #else
#define IOREMAP_TOP KVIRT_TOP #define IOREMAP_TOP FIXADDR_START
#endif #endif
/* PPC32 shares vmalloc area with ioremap */ /* PPC32 shares vmalloc area with ioremap */
......
...@@ -76,21 +76,15 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); ...@@ -76,21 +76,15 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot);
*/ */
#include <asm/fixmap.h> #include <asm/fixmap.h>
#ifdef CONFIG_HIGHMEM
#define KVIRT_TOP PKMAP_BASE
#else
#define KVIRT_TOP FIXADDR_START
#endif
/* /*
* ioremap_bot starts at that address. Early ioremaps move down from there, * ioremap_bot starts at that address. Early ioremaps move down from there,
* until mem_init() at which point this becomes the top of the vmalloc * until mem_init() at which point this becomes the top of the vmalloc
* and ioremap space * and ioremap space
*/ */
#ifdef CONFIG_NOT_COHERENT_CACHE #ifdef CONFIG_HIGHMEM
#define IOREMAP_TOP ((KVIRT_TOP - CONFIG_CONSISTENT_SIZE) & PAGE_MASK) #define IOREMAP_TOP PKMAP_BASE
#else #else
#define IOREMAP_TOP KVIRT_TOP #define IOREMAP_TOP FIXADDR_START
#endif #endif
/* PPC32 shares vmalloc area with ioremap */ /* PPC32 shares vmalloc area with ioremap */
......
...@@ -4,310 +4,18 @@ ...@@ -4,310 +4,18 @@
* Copyright (C) 2001 Dan Malek (dmalek@jlc.net) * Copyright (C) 2001 Dan Malek (dmalek@jlc.net)
* *
* Copyright (C) 2000 Russell King * Copyright (C) 2000 Russell King
*
* Consistent memory allocators. Used for DMA devices that want to
* share uncached memory with the processor core. The function return
* is the virtual address and 'dma_handle' is the physical address.
* Mostly stolen from the ARM port, with some changes for PowerPC.
* -- Dan
*
* Reorganized to get rid of the arch-specific consistent_* functions
* and provide non-coherent implementations for the DMA API. -Matt
*
* Added in_interrupt() safe dma_alloc_coherent()/dma_free_coherent()
* implementation. This is pulled straight from ARM and barely
* modified. -Matt
*/ */
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/kernel.h> #include <linux/kernel.h>
#include <linux/errno.h> #include <linux/errno.h>
#include <linux/string.h>
#include <linux/types.h> #include <linux/types.h>
#include <linux/highmem.h> #include <linux/highmem.h>
#include <linux/dma-direct.h> #include <linux/dma-direct.h>
#include <linux/dma-noncoherent.h> #include <linux/dma-noncoherent.h>
#include <linux/export.h>
#include <asm/tlbflush.h> #include <asm/tlbflush.h>
#include <asm/dma.h> #include <asm/dma.h>
#include <mm/mmu_decl.h>
/*
* This address range defaults to a value that is safe for all
* platforms which currently set CONFIG_NOT_COHERENT_CACHE. It
* can be further configured for specific applications under
* the "Advanced Setup" menu. -Matt
*/
#define CONSISTENT_BASE (IOREMAP_TOP)
#define CONSISTENT_END (CONSISTENT_BASE + CONFIG_CONSISTENT_SIZE)
#define CONSISTENT_OFFSET(x) (((unsigned long)(x) - CONSISTENT_BASE) >> PAGE_SHIFT)
/*
* This is the page table (2MB) covering uncached, DMA consistent allocations
*/
static DEFINE_SPINLOCK(consistent_lock);
/*
* VM region handling support.
*
* This should become something generic, handling VM region allocations for
* vmalloc and similar (ioremap, module space, etc).
*
* I envisage vmalloc()'s supporting vm_struct becoming:
*
* struct vm_struct {
* struct vm_region region;
* unsigned long flags;
* struct page **pages;
* unsigned int nr_pages;
* unsigned long phys_addr;
* };
*
* get_vm_area() would then call vm_region_alloc with an appropriate
* struct vm_region head (eg):
*
* struct vm_region vmalloc_head = {
* .vm_list = LIST_HEAD_INIT(vmalloc_head.vm_list),
* .vm_start = VMALLOC_START,
* .vm_end = VMALLOC_END,
* };
*
* However, vmalloc_head.vm_start is variable (typically, it is dependent on
* the amount of RAM found at boot time.) I would imagine that get_vm_area()
* would have to initialise this each time prior to calling vm_region_alloc().
*/
struct ppc_vm_region {
struct list_head vm_list;
unsigned long vm_start;
unsigned long vm_end;
};
static struct ppc_vm_region consistent_head = {
.vm_list = LIST_HEAD_INIT(consistent_head.vm_list),
.vm_start = CONSISTENT_BASE,
.vm_end = CONSISTENT_END,
};
static struct ppc_vm_region *
ppc_vm_region_alloc(struct ppc_vm_region *head, size_t size, gfp_t gfp)
{
unsigned long addr = head->vm_start, end = head->vm_end - size;
unsigned long flags;
struct ppc_vm_region *c, *new;
new = kmalloc(sizeof(struct ppc_vm_region), gfp);
if (!new)
goto out;
spin_lock_irqsave(&consistent_lock, flags);
list_for_each_entry(c, &head->vm_list, vm_list) {
if ((addr + size) < addr)
goto nospc;
if ((addr + size) <= c->vm_start)
goto found;
addr = c->vm_end;
if (addr > end)
goto nospc;
}
found:
/*
* Insert this entry _before_ the one we found.
*/
list_add_tail(&new->vm_list, &c->vm_list);
new->vm_start = addr;
new->vm_end = addr + size;
spin_unlock_irqrestore(&consistent_lock, flags);
return new;
nospc:
spin_unlock_irqrestore(&consistent_lock, flags);
kfree(new);
out:
return NULL;
}
static struct ppc_vm_region *ppc_vm_region_find(struct ppc_vm_region *head, unsigned long addr)
{
struct ppc_vm_region *c;
list_for_each_entry(c, &head->vm_list, vm_list) {
if (c->vm_start == addr)
goto out;
}
c = NULL;
out:
return c;
}
/*
* Allocate DMA-coherent memory space and return both the kernel remapped
* virtual and bus address for that space.
*/
void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
gfp_t gfp, unsigned long attrs)
{
struct page *page;
struct ppc_vm_region *c;
unsigned long order;
u64 mask = ISA_DMA_THRESHOLD, limit;
if (dev) {
mask = dev->coherent_dma_mask;
/*
* Sanity check the DMA mask - it must be non-zero, and
* must be able to be satisfied by a DMA allocation.
*/
if (mask == 0) {
dev_warn(dev, "coherent DMA mask is unset\n");
goto no_page;
}
if ((~mask) & ISA_DMA_THRESHOLD) {
dev_warn(dev, "coherent DMA mask %#llx is smaller "
"than system GFP_DMA mask %#llx\n",
mask, (unsigned long long)ISA_DMA_THRESHOLD);
goto no_page;
}
}
size = PAGE_ALIGN(size);
limit = (mask + 1) & ~mask;
if ((limit && size >= limit) ||
size >= (CONSISTENT_END - CONSISTENT_BASE)) {
printk(KERN_WARNING "coherent allocation too big (requested %#x mask %#Lx)\n",
size, mask);
return NULL;
}
order = get_order(size);
/* Might be useful if we ever have a real legacy DMA zone... */
if (mask != 0xffffffff)
gfp |= GFP_DMA;
page = alloc_pages(gfp, order);
if (!page)
goto no_page;
/*
* Invalidate any data that might be lurking in the
* kernel direct-mapped region for device DMA.
*/
{
unsigned long kaddr = (unsigned long)page_address(page);
memset(page_address(page), 0, size);
flush_dcache_range(kaddr, kaddr + size);
}
/*
* Allocate a virtual address in the consistent mapping region.
*/
c = ppc_vm_region_alloc(&consistent_head, size,
gfp & ~(__GFP_DMA | __GFP_HIGHMEM));
if (c) {
unsigned long vaddr = c->vm_start;
struct page *end = page + (1 << order);
split_page(page, order);
/*
* Set the "dma handle"
*/
*dma_handle = phys_to_dma(dev, page_to_phys(page));
do {
SetPageReserved(page);
map_kernel_page(vaddr, page_to_phys(page),
pgprot_noncached(PAGE_KERNEL));
page++;
vaddr += PAGE_SIZE;
} while (size -= PAGE_SIZE);
/*
* Free the otherwise unused pages.
*/
while (page < end) {
__free_page(page);
page++;
}
return (void *)c->vm_start;
}
if (page)
__free_pages(page, order);
no_page:
return NULL;
}
/*
* free a page as defined by the above mapping.
*/
void arch_dma_free(struct device *dev, size_t size, void *vaddr,
dma_addr_t dma_handle, unsigned long attrs)
{
struct ppc_vm_region *c;
unsigned long flags, addr;
size = PAGE_ALIGN(size);
spin_lock_irqsave(&consistent_lock, flags);
c = ppc_vm_region_find(&consistent_head, (unsigned long)vaddr);
if (!c)
goto no_area;
if ((c->vm_end - c->vm_start) != size) {
printk(KERN_ERR "%s: freeing wrong coherent size (%ld != %d)\n",
__func__, c->vm_end - c->vm_start, size);
dump_stack();
size = c->vm_end - c->vm_start;
}
addr = c->vm_start;
do {
pte_t *ptep;
unsigned long pfn;
ptep = pte_offset_kernel(pmd_offset(pud_offset(pgd_offset_k(addr),
addr),
addr),
addr);
if (!pte_none(*ptep) && pte_present(*ptep)) {
pfn = pte_pfn(*ptep);
pte_clear(&init_mm, addr, ptep);
if (pfn_valid(pfn)) {
struct page *page = pfn_to_page(pfn);
__free_reserved_page(page);
}
}
addr += PAGE_SIZE;
} while (size -= PAGE_SIZE);
flush_tlb_kernel_range(c->vm_start, c->vm_end);
list_del(&c->vm_list);
spin_unlock_irqrestore(&consistent_lock, flags);
kfree(c);
return;
no_area:
spin_unlock_irqrestore(&consistent_lock, flags);
printk(KERN_ERR "%s: trying to free invalid coherent area: %p\n",
__func__, vaddr);
dump_stack();
}
/* /*
* make an area consistent. * make an area consistent.
*/ */
...@@ -408,23 +116,15 @@ void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, ...@@ -408,23 +116,15 @@ void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
__dma_sync_page(paddr, size, dir); __dma_sync_page(paddr, size, dir);
} }
/* void arch_dma_prep_coherent(struct page *page, size_t size)
* Return the PFN for a given cpu virtual address returned by arch_dma_alloc.
*/
long arch_dma_coherent_to_pfn(struct device *dev, void *vaddr,
dma_addr_t dma_addr)
{ {
/* This should always be populated, so we don't test every unsigned long kaddr = (unsigned long)page_address(page);
* level. If that fails, we'll have a nice crash which
* will be as good as a BUG_ON()
*/
unsigned long cpu_addr = (unsigned long)vaddr;
pgd_t *pgd = pgd_offset_k(cpu_addr);
pud_t *pud = pud_offset(pgd, cpu_addr);
pmd_t *pmd = pmd_offset(pud, cpu_addr);
pte_t *ptep = pte_offset_kernel(pmd, cpu_addr);
if (pte_none(*ptep) || !pte_present(*ptep)) flush_dcache_range(kaddr, kaddr + size);
return 0; }
return pte_pfn(*ptep);
static int __init atomic_pool_init(void)
{
return dma_atomic_pool_init(GFP_KERNEL, pgprot_noncached(PAGE_KERNEL));
} }
postcore_initcall(atomic_pool_init);
...@@ -302,10 +302,6 @@ void __init mem_init(void) ...@@ -302,10 +302,6 @@ void __init mem_init(void)
pr_info(" * 0x%08lx..0x%08lx : highmem PTEs\n", pr_info(" * 0x%08lx..0x%08lx : highmem PTEs\n",
PKMAP_BASE, PKMAP_ADDR(LAST_PKMAP)); PKMAP_BASE, PKMAP_ADDR(LAST_PKMAP));
#endif /* CONFIG_HIGHMEM */ #endif /* CONFIG_HIGHMEM */
#ifdef CONFIG_NOT_COHERENT_CACHE
pr_info(" * 0x%08lx..0x%08lx : consistent mem\n",
IOREMAP_TOP, IOREMAP_TOP + CONFIG_CONSISTENT_SIZE);
#endif /* CONFIG_NOT_COHERENT_CACHE */
if (ioremap_bot != IOREMAP_TOP) if (ioremap_bot != IOREMAP_TOP)
pr_info(" * 0x%08lx..0x%08lx : early ioremap\n", pr_info(" * 0x%08lx..0x%08lx : early ioremap\n",
ioremap_bot, IOREMAP_TOP); ioremap_bot, IOREMAP_TOP);
......
...@@ -84,10 +84,6 @@ static struct addr_marker address_markers[] = { ...@@ -84,10 +84,6 @@ static struct addr_marker address_markers[] = {
#else #else
{ 0, "Early I/O remap start" }, { 0, "Early I/O remap start" },
{ 0, "Early I/O remap end" }, { 0, "Early I/O remap end" },
#ifdef CONFIG_NOT_COHERENT_CACHE
{ 0, "Consistent mem start" },
{ 0, "Consistent mem end" },
#endif
#ifdef CONFIG_HIGHMEM #ifdef CONFIG_HIGHMEM
{ 0, "Highmem PTEs start" }, { 0, "Highmem PTEs start" },
{ 0, "Highmem PTEs end" }, { 0, "Highmem PTEs end" },
...@@ -335,11 +331,6 @@ static void populate_markers(void) ...@@ -335,11 +331,6 @@ static void populate_markers(void)
#else /* !CONFIG_PPC64 */ #else /* !CONFIG_PPC64 */
address_markers[i++].start_address = ioremap_bot; address_markers[i++].start_address = ioremap_bot;
address_markers[i++].start_address = IOREMAP_TOP; address_markers[i++].start_address = IOREMAP_TOP;
#ifdef CONFIG_NOT_COHERENT_CACHE
address_markers[i++].start_address = IOREMAP_TOP;
address_markers[i++].start_address = IOREMAP_TOP +
CONFIG_CONSISTENT_SIZE;
#endif
#ifdef CONFIG_HIGHMEM #ifdef CONFIG_HIGHMEM
address_markers[i++].start_address = PKMAP_BASE; address_markers[i++].start_address = PKMAP_BASE;
address_markers[i++].start_address = PKMAP_ADDR(LAST_PKMAP); address_markers[i++].start_address = PKMAP_ADDR(LAST_PKMAP);
......
...@@ -460,8 +460,10 @@ config NOT_COHERENT_CACHE ...@@ -460,8 +460,10 @@ config NOT_COHERENT_CACHE
depends on 4xx || PPC_8xx || E200 || PPC_MPC512x || \ depends on 4xx || PPC_8xx || E200 || PPC_MPC512x || \
GAMECUBE_COMMON || AMIGAONE GAMECUBE_COMMON || AMIGAONE
select ARCH_HAS_DMA_COHERENT_TO_PFN select ARCH_HAS_DMA_COHERENT_TO_PFN
select ARCH_HAS_DMA_PREP_COHERENT
select ARCH_HAS_SYNC_DMA_FOR_DEVICE select ARCH_HAS_SYNC_DMA_FOR_DEVICE
select ARCH_HAS_SYNC_DMA_FOR_CPU select ARCH_HAS_SYNC_DMA_FOR_CPU
select DMA_DIRECT_REMAP
default n if PPC_47x default n if PPC_47x
default y default y
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment